Utilizing Machine Learning to Reconnect Potential Customers of the E-Commerce Industry

In competitive markets, it is costly to attract new customers in the business as they already have a wide customer base; that being the case, businesses spend a healthy budget to reconnect with customers they have had transactions with in the past. As we are approaching towards post-pandemic, there is a need to increase the profitability of the businesses and retain their customer base. To increase customer turnover and re-engagement, this paper focuses on the implementation of intelligent business practices using machine learning and neural networks. The paper focuses on analyzing the customer behavior based on their purchase behavior and purchase transactional values for customer retention. The division is done to identify the customers who are profitable to the business and customers who are likely to churn for a number of reasons. In this paper, we proposed a Multi-layer perceptron (MLP) to segment the customers according to Recency, Frequency, and Monetary Value (RFM) methodology and customer profitability index. The result of MLP was compared with K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) as the later models have been widely used. Additionally, Bidirectional Long Short-Term Memory (Bi-LSTM) models have been implemented for primary customer classification and sales prediction. The prediction model is an attempt to reduce the financial loss on marketing campaigns for re-engagement of customers in the business. The dataset used was retrieved from Cardinal Care BD.